4 December 1998 Optimized combination, regularization, and pruning in parallel consensual neural networks
Author Affiliations +
Proceedings Volume 3500, Image and Signal Processing for Remote Sensing IV; (1998); doi: 10.1117/12.331874
Event: Remote Sensing, 1998, Barcelona, Spain
Abstract
Optimized combination, regularization, and pruning is proposed for the Parallel Consensual Neural Networks (PC-NNs) which is a neural network architecture based on the consensus of a collection of stage neural networks trained on the same input data with different representations. Here, a regularization scheme is presented for the PCNN and in training a regularized cost function is minimized. The use of this regularization scheme in conjunction with Optimal Brain Damage pruning is suggested both to optimize the architecture of the individual stage networks and to avoid overfitting. Experiments are conducted on a multisource remote sensing and geographic data set consisting of six data source. The results obtained by the proposed version of PCNN are compared to other classification approaches such as the original PCNN, single stage neural networks and statistical classifiers. In comparison to the originally proposed PCNNs, the use of pruning and regularization not only produces simpler PCNNs but also gives higher classification accuracies. In particular, using the proposed approach, a neural network based non-linear combination scheme, for the individual stages in the PCNN, produces excellent overall classification accuracies for both training and test data.
© (1998) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jon Atli Benediktsson, Jan Larsen, Johannes R. Sveinsson, L. K. Hansen, "Optimized combination, regularization, and pruning in parallel consensual neural networks", Proc. SPIE 3500, Image and Signal Processing for Remote Sensing IV, (4 December 1998); doi: 10.1117/12.331874; https://doi.org/10.1117/12.331874
PROCEEDINGS
11 PAGES


SHARE
KEYWORDS
Neural networks

Data modeling

Neurons

Remote sensing

Network architectures

Brain

Error analysis

Back to Top